Supporting analysis of future-related information in news archives and the web

ABSTRACT

A lot of future-related information is available in news articles or Web pages. This information can however differ to large extent and may fluctuate over time. It is therefore difficult for users to manually compare and aggregate it, and to re-construct the most probable course of future events. In this paper we approach a problem of automatically generating summaries of future events related to queries using data obtained from news archive collections or from the Web. We propose two methods, explicit and implicit future-related information detection. The former is based on analyzing the context of future temporal expressions in documents, while the latter relies on detecting periodical patterns in historical document collections. We present a graph-based visualization of future-related information and demonstrate its usefulness through several examples.

REFERENCES

• 1: R. Baeza-Yates. Searching the Future. Proceedings of ACM SIGIR Workshop on Mathematical/Formal Methods in Information Retrieval (MF/IR 2005), 2005.
• 2: T. Calinski and J. Harabasz. A Dendrite Method for Cluster Analysis. Communications in Statistics, vol. 3, no.1, pp.1--27, 1974.
• 3: Munmun De Choudhury , Hari Sundaram , Ajita John , Dorée Duncan Seligmann, Can blog communication dynamics be correlated with stock market activity?, Proceedings of the nineteenth ACM conference on Hypertext and hypermedia, June 19-21, 2008, Pittsburgh, PA, USA [doi>10.1145/1379092.1379106]
• 4: Daniel Gruhl , R. Guha , Ravi Kumar , Jasmine Novak , Andrew Tomkins, The predictive power of online chatter, Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining, August 21-24, 2005, Chicago, Illinois, USA [doi>10.1145/1081870.1081883]
• 5: Adam Jatowt , Yukiko Kawai , Katsumi Tanaka, Detecting age of page content, Proceedings of the 9th annual ACM international workshop on Web information and data management, November 09-09, 2007, Lisbon, Portugal [doi>10.1145/1316902.1316925]
• 6: R. Kimura, S. Oyama, H. Toda and K. Tanaka. Creating Personal Histories from the Web using Namesake Disambiguation and Event Extraction. Proceedings of the 7th International Conference on Web Engineering, pp. 400--414, 2007.
• 7: Yang Liu , Xiangji Huang , Aijun An , Xiaohui Yu, ARSA: a sentiment-aware model for predicting sales performance using blogs, Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, July 23-27, 2007, Amsterdam, The Netherlands [doi>10.1145/1277741.1277845]
• 8: G. Mishne and N. Glance. Predicting Movie Sales from Blogger Sentiment. Proceedings of the Spring Symposia on Computational Approaches to Analyzing Weblogs, 2006.
• 9: Marius Paşca, Lightweight web-based fact repositories for textual question answering, Proceedings of the sixteenth ACM conference on Conference on information and knowledge management, November 06-10, 2007, Lisbon, Portugal [doi>10.1145/1321440.1321455]
• 10: A. Pepe and J. Bollen. Between Conjecture and Memento: Shaping a Collective Emotional Perception of the Future. Proceedings of the AAAI 2008 Spring Symposium on Emotion, Personality and Social Behavior, 2008.
• 11: B. Wuthrich, D. Permunetilleke, S. Leung, V. Cho, J. Zhang and W. Lam. Daily Prediction of Major Stock Indices from textual WWW Data. Proceedings of the 4th International Conference on Knowledge Discovery and Data Mining, pp.364--368, 1998.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval

General Terms:
Algorithms

Keywords:
event prediction, future-related information retrieval, temporal information analysis